CN113555141A - Intelligent monitoring method and system for nuclear power station and intelligent monitoring server - Google Patents
Intelligent monitoring method and system for nuclear power station and intelligent monitoring server Download PDFInfo
- Publication number
- CN113555141A CN113555141A CN202110812520.2A CN202110812520A CN113555141A CN 113555141 A CN113555141 A CN 113555141A CN 202110812520 A CN202110812520 A CN 202110812520A CN 113555141 A CN113555141 A CN 113555141A
- Authority
- CN
- China
- Prior art keywords
- nuclear power
- power station
- artificial intelligence
- intelligent monitoring
- intelligence program
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 111
- 238000000034 method Methods 0.000 title claims abstract description 65
- 230000008569 process Effects 0.000 claims abstract description 26
- 238000012545 processing Methods 0.000 claims description 19
- 238000012549 training Methods 0.000 claims description 15
- 238000010276 construction Methods 0.000 claims description 12
- 230000002787 reinforcement Effects 0.000 claims description 9
- 238000005457 optimization Methods 0.000 claims description 8
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 17
- 238000013473 artificial intelligence Methods 0.000 description 13
- 238000005516 engineering process Methods 0.000 description 12
- 230000001276 controlling effect Effects 0.000 description 9
- 239000007788 liquid Substances 0.000 description 7
- 238000012546 transfer Methods 0.000 description 7
- 230000006870 function Effects 0.000 description 5
- 230000006872 improvement Effects 0.000 description 4
- 238000002347 injection Methods 0.000 description 4
- 239000007924 injection Substances 0.000 description 4
- 238000005259 measurement Methods 0.000 description 3
- 230000001105 regulatory effect Effects 0.000 description 3
- 238000001816 cooling Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 239000003381 stabilizer Substances 0.000 description 2
- 230000006399 behavior Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000011217 control strategy Methods 0.000 description 1
- 238000005336 cracking Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000007599 discharging Methods 0.000 description 1
- 238000002955 isolation Methods 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 238000011017 operating method Methods 0.000 description 1
- 238000013486 operation strategy Methods 0.000 description 1
- 238000011112 process operation Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 239000000243 solution Substances 0.000 description 1
- 239000007921 spray Substances 0.000 description 1
- 238000005507 spraying Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 230000001052 transient effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G21—NUCLEAR PHYSICS; NUCLEAR ENGINEERING
- G21D—NUCLEAR POWER PLANT
- G21D3/00—Control of nuclear power plant
- G21D3/007—Expert systems
-
- G—PHYSICS
- G21—NUCLEAR PHYSICS; NUCLEAR ENGINEERING
- G21D—NUCLEAR POWER PLANT
- G21D3/00—Control of nuclear power plant
- G21D3/001—Computer implemented control
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E30/00—Energy generation of nuclear origin
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Plasma & Fusion (AREA)
- High Energy & Nuclear Physics (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The invention provides an intelligent monitoring method of a nuclear power station, which comprises the following steps: receiving monitoring data sent by a nuclear power station instrument control system in real time; calling an automation program or an artificial intelligence program model according to a preset running rule target and real-time received monitoring data and a sequence control logic of the running rule to generate a control instruction required for executing each step in the sequence control logic of the running rule; and sending the control instruction to the instrument control system of the nuclear power station in real time to execute corresponding control so as to realize the autonomous execution of the operation rule. Correspondingly, an intelligent monitoring server and an intelligent monitoring system of the nuclear power station are also provided. The intelligent monitoring method can solve the current situation that the current nuclear power station still needs operating personnel to process operating regulations, and is used for realizing intelligent monitoring of the nuclear power station and improving the operating efficiency and safety.
Description
Technical Field
The invention relates to the technical field of nuclear power, in particular to an intelligent monitoring method and system for a nuclear power station and an intelligent monitoring server.
Background
The improvement of the operation efficiency of the nuclear power station depends on the improvement of the automation level to a great extent, the digitization of an instrument control system is already realized in the design of the current nuclear power station, so that the transmission and processing capacity of the instrument control system on data is obviously improved, the automation level and the operation efficiency of the nuclear power station are improved by the traditional control methods such as PID (proportional Integral Differential) closed-loop regulation, sequential control and the like, but the complexity of the nuclear power station system and the fault mode thereof still highly depends on the experience and the processing of operators when the expected operation events and accidents are handled.
At present, although some basic artificial intelligence systems (such as expert systems based on fixed logic, auxiliary decision and fault diagnosis systems) are applied to the field of nuclear power plant operation, the artificial intelligence systems play a role in assisting operators in monitoring a power plant. However, due to the special safety requirements of the nuclear power plant and the complexity of the operation tasks, many task functions which are difficult to describe through a formula exist, the judgment and the control are still required to be performed by the operation personnel, the operation efficiency is low, and human errors exist, so that an intelligent monitoring method is urgently needed for reducing the workload of the operation personnel and improving the operation efficiency and the safety of the nuclear power plant.
Disclosure of Invention
The technical problem to be solved by the present invention is to provide an intelligent monitoring method and system for a nuclear power station, and an intelligent monitoring server, aiming at the above disadvantages in the prior art, which can solve the current situation that the current nuclear power station still needs operators to process operation regulations, and is used for realizing the intelligent monitoring of the nuclear power station.
In a first aspect, an embodiment of the present invention provides an intelligent monitoring method for a nuclear power station, including: receiving monitoring data sent by a nuclear power station instrument control system in real time; calling an automatic program or an artificial intelligent program model in a model library according to a preset running rule target and real-time received monitoring data and a sequence control logic of the running rule so as to generate a control instruction required for executing each step in the sequence control logic of the running rule; and sending the control instruction to the instrument control system of the nuclear power station in real time to execute corresponding control so as to realize the autonomous execution of the operation rule.
Preferably, before the receiving monitoring data sent by the nuclear power plant instrument control system in real time, the intelligent monitoring method for the nuclear power plant further includes: constructing a sequence control logic of the operation regulation according to an overall processing flow and a branch processing flow of the operation regulation of the nuclear power station, wherein the sequence control logic comprises N steps which are required to be executed in sequence when the operation regulation is executed, and N is a positive integer; and determining a generation main body of the control instruction corresponding to each step according to the characteristics of each step in the sequence control logic, wherein the generation main body comprises an automatic program or an artificial intelligence program model.
Preferably, before determining the generation subject of the control instruction corresponding to each step according to the characteristics of each step in the sequence control logic, the intelligent monitoring method for the nuclear power plant further includes: a model library is constructed, the model library including a plurality of artificial intelligence program models.
Preferably, constructing the model library specifically includes: constructing a structure of an artificial intelligence program model according to the configuration of the instrument control system of the nuclear power station and the judgment process when the mth step is manually executed, wherein m is less than or equal to N and is a positive integer; determining input variables of the artificial intelligence program model according to the monitored information during the artificial execution of the mth step; and carrying out supervised learning on the artificial intelligence program model based on historical data generated in the process of artificially executing the mth step to generate the artificial intelligence program model corresponding to the mth step, wherein the historical data comprises monitored information and/or control instructions.
Preferably, after the artificial intelligence program model is supervised and learned based on the historical data generated during the mth step of the artificial intelligence execution, so as to generate the artificial intelligence program model corresponding to the mth step, the intelligent monitoring method for the nuclear power plant further includes: and executing the monitoring task by the generated artificial intelligence program model corresponding to the mth step in the nuclear power station simulator, and collecting data generated in the process of executing the monitoring task to perform reinforcement learning so as to determine the optimal parameters of the artificial intelligence program model corresponding to the mth step.
In a second aspect, an embodiment of the present invention further provides an intelligent monitoring server for a nuclear power plant, including a receiving module, an executing module, a sending module, and a model library. And the receiving module is used for receiving the monitoring data sent by the instrument control system of the nuclear power station in real time. And the execution module is connected with the receiving module and used for calling an automatic program or an artificial intelligence program model in a model base according to the preset sequence control logic of the operation rule according to the preset operation rule target and the real-time received monitoring data so as to generate a control instruction required by executing each step in the sequence control logic of the operation rule. And the sending module is connected with the execution module and is used for sending the control instruction to the instrument control system of the nuclear power station in real time to execute corresponding control so as to realize the autonomous execution of the operation rules. And the model library is used for storing a plurality of artificial intelligence program models.
Preferably, the intelligent monitoring server further comprises a first building module, a determination module and a second building module. The first construction module is used for constructing the sequence control logic of the operation regulation according to the whole processing flow and the branch processing flow of the operation regulation of the nuclear power station, the sequence control logic comprises N steps which are required to be executed in sequence when the operation regulation is executed, and N is a positive integer. And the determining module is connected with the constructing module and is used for determining a generating main body of the control instruction corresponding to each step according to the characteristics of each step in the sequence control logic, and the generating main body comprises an automatic program or an artificial intelligence program model. And the second construction module is connected with the determination module and used for constructing a model library, and the model library comprises a plurality of artificial intelligence program models.
Preferably, the second building block comprises a building unit and a training unit. And the construction unit is used for constructing the structure of the artificial intelligence program model according to the configuration of the nuclear power station instrument control system and the judgment process when the mth step is manually executed, wherein m is less than or equal to N and is a positive integer, and the input variable of the artificial intelligence program model is determined according to the monitored information when the mth step is manually executed. And the training unit is connected with the construction unit and used for carrying out supervised learning on the artificial intelligent program model based on historical data generated in the process of artificially executing the mth step so as to generate the artificial intelligent program model corresponding to the mth step, wherein the historical data comprises monitored information and/or control instructions.
Preferably, the second building block further comprises an optimization unit. And the optimization unit is connected with the training unit and used for executing the monitoring task on the artificial intelligence program model corresponding to the mth step in the nuclear power plant simulator and collecting data generated in the process of executing the monitoring task to perform reinforcement learning so as to determine the optimal parameters of the artificial intelligence program model corresponding to the mth step.
In a third aspect, an embodiment of the present invention further provides an intelligent monitoring system for a nuclear power plant, including a nuclear power plant instrumentation and control system and the intelligent monitoring server for a nuclear power plant described in the second aspect. The nuclear power station instrument control system is used for monitoring operation data of equipment in the nuclear power station and sending the monitoring data to an intelligent monitoring server of the nuclear power station in real time. The intelligent monitoring server of the nuclear power station is connected with the nuclear power station instrument control system and used for receiving monitoring data sent by the nuclear power station instrument control system in real time and sending a control command to the nuclear power station instrument control system. And the nuclear power plant instrument control system is also used for executing corresponding control on corresponding equipment in the nuclear power plant according to the control command.
According to the intelligent monitoring method and system for the nuclear power station and the intelligent monitoring server, the automatic program or the artificial intelligent program model is called according to the sequence control logic of the preset operation regulation, the control instruction required for executing each step of the operation regulation is generated, and the control instruction is correspondingly controlled through the instrument control system of the nuclear power station, so that the autonomous execution of the operation regulation, namely the intelligent monitoring of the nuclear power plant is realized. The workload of operators can be reduced, and the operation efficiency and the safety of the nuclear power station are improved.
Drawings
Fig. 1 is a flowchart of an intelligent monitoring method for a nuclear power plant according to embodiment 1 of the present invention;
FIG. 2 is a sequence control logic of a procedure for handling a burst accident of a steam generator tube of a pressurized water reactor nuclear power plant according to example 1 of the present invention;
fig. 3 is a schematic diagram of an artificial intelligence program model according to embodiment 1 of the present invention.
Detailed Description
In order to make the technical solutions of the present invention better understood, the present invention is further described in detail below with reference to the accompanying drawings and examples.
Example 1:
as shown in fig. 1, this embodiment provides an intelligent monitoring method for a nuclear power plant, which is applicable to control of operating procedures of different nuclear power plants, and the intelligent monitoring method includes:
In this embodiment, the instrument control system of the nuclear power plant has the measurement and control functions of the measurement instrument, and data processing and communication capabilities. The monitoring data refers to measurement data of a measuring instrument, such as auxiliary feedwater flow, steam flow, blowdown flow, main feedwater flow and the like, acquired by a nuclear power plant instrument control system in real time in a monitoring process.
And 102, calling an automatic program or an artificial intelligence program model in a model base according to a preset sequence control logic of the operation rule according to a preset operation rule target and the monitoring data received in real time so as to generate a control instruction required for executing each step in the sequence control logic of the operation rule.
In the present embodiment, the automation program refers to a program designed in accordance with a predetermined rule, and the artificial intelligence program model refers to a program model designed to simulate the behavior of a human being.
Specifically, at step 101: before receiving monitoring data sent by a nuclear power station instrument control system in real time, the intelligent monitoring method of the nuclear power station further comprises the following steps:
and step S10, constructing a sequence control logic of the operation regulation according to the whole processing flow and the branch processing flow of the operation regulation of the nuclear power station, wherein the sequence control logic comprises N steps which are required to be executed in sequence when the operation regulation is executed, and N is a positive integer.
And step S11, determining a generation main body of the control instruction corresponding to each step according to the characteristics of each step in the sequence control logic, wherein the generation main body comprises an automatic program or an artificial intelligence program model. For example, a series of isolation valves need to be opened in sequence in the nuclear power starting process of the pressurized water reactor, the step can be realized by the traditional automation technology, and the generation subject of the control instruction corresponding to the step is determined to be an automation program; for the regulation of the loop pressure under an unstable transient state in the starting process, parameters need to be observed and judged manually, and the parameters need to be observed and judged by an artificial intelligence technology, so that the generation main body of the control instruction corresponding to the step is determined to be an artificial intelligence program model.
In the present embodiment, the method of the present embodiment will be described by taking an operating schedule for handling a burst accident of a steam generator heat transfer tube of a pressurized water reactor nuclear power plant as an example. The method comprises the steps of constructing a sequence control logic of an operation rule according to all processing flows (namely an integral processing flow and branch processing flows) of the operation rule of the steam generator heat transfer pipe rupture accident, wherein the sequence control logic is used for realizing all processing flows of a certain operation rule through a sequence control logic, the sequence control logic comprises N steps, and the content of each step in the sequence control logic is defined. As shown in fig. 2, the configured sequential control logic includes 13 steps to be sequentially executed: the method comprises the steps of cracking a heat transfer pipe of a steam generator, triggering shutdown and safety injection signals in sequence, automatically confirming after shutdown and safety injection, diagnosing and confirming an accident steam generator, waiting for the completion of quick cooling, isolating the damaged steam generator, controlling the water level of the steam generator, stopping a low-pressure safety injection pump, controlling primary loop cooling, spraying a voltage stabilizer to control primary loop pressure reduction, stopping the medium-pressure safety injection pump, establishing charging and discharging, and controlling primary loop pressure and charging flow. For each step shown in fig. 2 (i.e., the sequence control logic of the constructed operating protocol), it is determined which steps are suitable for using conventional automation techniques (corresponding to an automation program) or which steps require the use of artificial intelligence techniques (corresponding to an artificial intelligence program model) to generate the control instructions required to perform the monitoring task, based on the configuration of the plant instrumentation and the characteristics of each step in the sequence control logic. Through analysis, the following 4 steps need to be completed by using an artificial intelligence technology, and the other 9 steps use an automation program to realize the generation of control instructions:
(1) controlling the water level of the steam generator;
(2) controlling a loop to cool;
(3) the voltage stabilizer sprays to control a loop to reduce the voltage;
(4) and controlling the pressure and the upper charging flow of the primary circuit.
Then, monitoring data sent by the nuclear power plant instrument control system in real time is received, an automation program or an artificial intelligence program model in a model library is called according to a preset operation regulation target (namely a monitoring task target) and the monitoring data received in real time, and control instructions required for executing 13 steps in the sequence control logic of the operation regulation of the steam generator heat transfer pipe rupture accident are generated in real time according to the sequence control logic of the operation regulation illustrated in fig. 2, so that the operation regulation of the steam generator heat transfer pipe rupture accident is automatically executed.
Alternatively, at step S11: before determining the generation subject of the control instruction corresponding to each step according to the characteristics of each step in the sequence control logic, the intelligent monitoring method further comprises the following steps: and constructing a model library, wherein the model library comprises a plurality of artificial intelligence program models.
Specifically, constructing the model library includes:
step S21: and constructing a structure of an artificial intelligence program model according to the configuration of the instrument control system of the nuclear power station and the judgment process when the mth step is manually executed, wherein m is less than or equal to N and is a positive integer.
Step S22: input variables of the artificial intelligence program model are determined from information monitored during the artificial execution of the mth step.
And step S23, performing supervised learning on the artificial intelligence program model based on historical data generated in the process of executing the mth step manually to generate the artificial intelligence program model corresponding to the mth step, wherein the historical data comprises monitored information and/or control instructions.
In this embodiment, since there are four steps of using the artificial intelligence technology, four artificial intelligence program models are required to be generated for the operation rule of the steam generator heat transfer tube rupture accident in this embodiment. To better explain the specific process of constructing the model library, the seventh step (i.e., m is 7, controlling the steam generator level) is taken as an example in the sequential control logic of the operating protocol to explain the method of the embodiment. In order to realize intelligent monitoring for controlling the water level of the steam generator, an artificial intelligence program model is first constructed according to the configuration of the instrumentation and control system of the nuclear power plant and the judgment flow (or thinking mode) of a human in the step of controlling the water level of the steam generator, as shown in fig. 3. The artificial judgment process corresponding to the structure of the artificial intelligence program model is as follows: firstly, calculating the actual net flow of the steam generator according to parameters such as the liquid level change condition of the steam generator, the auxiliary water supply flow, the steam flow, the pollution discharge flow, the main water supply flow and the like; then, calculating the target net flow of the steam generator according to the deviation of the actual liquid level and the target liquid level of the steam generator; further calculating the target flow of the auxiliary water supply according to the difference between the current auxiliary water supply flow and the actual net flow and the target net flow; then, the opening degree of the auxiliary water supply regulating valve required for reaching the target flow is judged through a multilayer neural network model; and finally, executing corresponding control (namely outputting the opening of the target regulating valve to the instrument control system of the nuclear power station so as to perform corresponding control) according to the judgment result of the artificial intelligence program model. The input variables of the artificial intelligence program model are determined according to monitoring information which needs to be considered when the step is executed artificially, and the method comprises the following steps:
(1) steam generator level;
(2) auxiliary water supply flow rate;
(3) auxiliary water supply line pressure;
(4) opening degree of an auxiliary water supply flow regulating valve;
(5) the steam pressure.
After the structure and input variables of the artificial intelligence program model are determined, supervised learning (i.e. training) is performed on the model: firstly, collecting data records when the seventh step is executed during artificial training on the simulator of the nuclear power plant (the data records comprise system states such as liquid level of a steam generator, auxiliary water supply flow, auxiliary water supply pipeline pressure, steam pressure and the like when the seventh step is executed artificially, control instructions given artificially in the states, and influence data of the control instructions on the system states). It should be noted that, because a steam generator heat transfer tube breakage accident rarely occurs in an actual nuclear power plant, the data records are mainly training data of a nuclear power plant simulator, and supervised learning is performed by using the data records, so that the artificial intelligence program model initially has the capability of executing an operation monitoring task (i.e. the same or similar judgment as a human can be made under the condition of the same or similar training data, but the judgment is inaccurate or the wrong judgment is generated under other different conditions).
Alternatively, at step S23: after the artificial intelligence program model is supervised and learned based on the historical data generated in the process of artificially executing the mth step to generate the artificial intelligence program model corresponding to the mth step, the intelligent monitoring method of the nuclear power station further comprises the following steps: and executing the monitoring task by the generated artificial intelligence program model corresponding to the mth step in the nuclear power station simulator, and collecting data generated in the process of executing the monitoring task to perform reinforcement learning so as to determine the optimal parameters of the artificial intelligence program model corresponding to the mth step.
In this embodiment, the artificial intelligence program model executes the operation monitoring task in the nuclear power plant simulator, collects data generated in the operation monitoring process, performs reinforcement learning, and optimizes parameters of the artificial intelligence program model in the reinforcement learning process, so as to improve performance and efficiency of executing the operation monitoring task. The control command given by the artificial intelligence program is more effective by adjusting the parameters of the artificial intelligence program model. For example, in the present embodiment, the deviation between the actual liquid level of the steam generator and the target liquid level and the speed of reaching the target liquid level are used as indexes for measuring performance and efficiency, so that the artificial intelligence program model has the capability of efficiently and autonomously performing the operation monitoring task.
And 103, sending the control instruction to the instrument control system of the nuclear power station in real time to execute corresponding control so as to realize the autonomous execution of the operation regulation.
In summary, the intelligent monitoring method of this embodiment is implemented by using a sequence control logic form for the whole flow and the branch flow in the operation procedure of the nuclear power plant, and determines to generate a corresponding control instruction by an automation technology or an artificial intelligence technology according to the specific characteristics of each step in the sequence control logic of the operation procedure, thereby implementing an autonomous monitoring function. For tasks needing to be finished through an artificial intelligence technology, an artificial intelligence program model is firstly established according to a task principle, then supervised learning is carried out by utilizing artificial operation records, then the artificial intelligence model executes control tasks on a simulation machine and carries out reinforcement learning, and finally the artificial intelligence program model has the capability equivalent to the capability of manually executing operation tasks. The intelligent monitoring method can make up for the short board of the traditional automation technology when the function of the task is complex and is difficult to describe by a fixed formula. The mode of combining the traditional automation technology and the artificial intelligence technology can effectively improve the automation level and the operation efficiency of the nuclear power station. Meanwhile, when the operator needs to process a large number of tasks in parallel, the workload of the operator can be reduced, the possibility of personnel error is indirectly reduced, and the safety of the nuclear power station is improved. In addition, the artificial intelligence technology has the capability of self optimization and expansion, and the introduction of the artificial intelligence technology can be used for optimizing the existing operation strategy and control method. The learning and training speed of the artificial intelligence program model for the specific task is higher than that of an operator, the artificial intelligence program model can be generated in batches, the proficiency is not weakened along with the lapse of time, the artificial intelligence program model can be used as an expert to guide an operator to complete an operation task in a more reasonable mode, meanwhile, defects and deficiencies in the existing control strategy can be found through comparison, and reference is provided for optimization of a nuclear power station monitoring function.
Example 2:
the embodiment provides an intelligent monitoring server of a nuclear power station, which comprises a receiving module, an execution module, a sending module and a model library.
And the receiving module is used for receiving the monitoring data sent by the instrument control system of the nuclear power station in real time.
And the execution module is connected with the receiving module and used for calling an automatic program or an artificial intelligence program model in a model base according to the preset sequence control logic of the operation rule according to the preset operation rule target and the real-time received monitoring data so as to generate a control instruction required by executing each step in the sequence control logic of the operation rule.
And the sending module is connected with the execution module and is used for sending the control instruction to the instrument control system of the nuclear power station in real time to execute corresponding control so as to realize the autonomous execution of the operation rules.
And the model library is used for storing a plurality of artificial intelligence program models.
Optionally, the intelligent monitoring server of the nuclear power plant further includes a first building module, a determining module, and a second building module.
The first construction module is used for constructing the sequence control logic of the operation regulation according to the whole processing flow and the branch processing flow of the operation regulation of the nuclear power station, the sequence control logic comprises N steps which are required to be executed in sequence when the operation regulation is executed, and N is a positive integer.
And the determining module is connected with the constructing module and is used for determining a generating main body of the control instruction corresponding to each step according to the characteristics of each step in the sequence control logic, and the generating main body comprises an automatic program or an artificial intelligence program model.
And the second construction module is connected with the determination module and used for constructing a model library, and the model library comprises a plurality of artificial intelligence program models.
Optionally, the second building block comprises a building unit and a training unit.
And the construction unit is used for constructing the structure of the artificial intelligence program model according to the configuration of the nuclear power station instrument control system and the judgment process when the mth step is manually executed, wherein m is less than or equal to N and is a positive integer, and the input variable of the artificial intelligence program model is determined according to the monitored information when the mth step is manually executed.
And the training unit is connected with the construction unit and used for carrying out supervised learning on the artificial intelligent program model based on historical data generated in the process of artificially executing the mth step so as to generate the artificial intelligent program model corresponding to the mth step, wherein the historical data comprises monitored information and/or control instructions.
Optionally, the second building block further comprises an optimization unit.
And the optimization unit is connected with the training unit and used for executing the monitoring task on the artificial intelligence program model corresponding to the mth step in the nuclear power plant simulator and collecting data generated in the process of executing the monitoring task to perform reinforcement learning so as to determine the optimal parameters of the artificial intelligence program model corresponding to the mth step.
Example 3:
the embodiment provides an intelligent monitoring system of a nuclear power station, which comprises a nuclear power station instrument control system and the intelligent monitoring server of the nuclear power station in the embodiment 2.
And the nuclear power station instrument control system is used for monitoring the operation data of equipment in the nuclear power station and sending the monitoring data to the intelligent monitoring server of the nuclear power station in real time.
And the intelligent monitoring server of the nuclear power station is connected with the nuclear power station instrument control system, and is used for receiving monitoring data sent by the nuclear power station instrument control system in real time and sending the control command to the nuclear power station instrument control system.
And the nuclear power plant instrument control system is also used for executing corresponding control on corresponding equipment in the nuclear power plant according to the control command.
In this embodiment, the intelligent monitoring system of the nuclear power station can be used alone or in cooperation with operators. In addition, the intelligent monitoring system of the nuclear power station is adopted to automatically execute the operation rules on the nuclear power station simulator so as to finish the training of operators.
It will be understood that the above embodiments are merely exemplary embodiments taken to illustrate the principles of the present invention, which is not limited thereto. It will be apparent to those skilled in the art that various modifications and improvements can be made without departing from the spirit and substance of the invention, and these modifications and improvements are also considered to be within the scope of the invention.
Claims (10)
1. An intelligent monitoring method for a nuclear power station is characterized by comprising the following steps:
receiving monitoring data sent by a nuclear power station instrument control system in real time;
calling an automatic program or an artificial intelligent program model in a model library according to a preset running rule target and real-time received monitoring data and a sequence control logic of the running rule so as to generate a control instruction required for executing each step in the sequence control logic of the running rule;
and sending the control instruction to the instrument control system of the nuclear power station in real time to execute corresponding control so as to realize the autonomous execution of the operation rule.
2. The intelligent monitoring method for nuclear power plants according to claim 1, further comprising, before the receiving the monitoring data transmitted in real time by the instrumentation and control system of the nuclear power plant:
constructing a sequence control logic of the operation regulation according to an overall processing flow and a branch processing flow of the operation regulation of the nuclear power station, wherein the sequence control logic comprises N steps which are required to be executed in sequence when the operation regulation is executed, and N is a positive integer;
and determining a generation main body of the control instruction corresponding to each step according to the characteristics of each step in the sequence control logic, wherein the generation main body comprises an automatic program or an artificial intelligence program model.
3. The intelligent monitoring method for a nuclear power plant according to claim 2, wherein before determining the generation subject of the control instruction corresponding to each step according to the characteristics of each step in the sequence control logic, the method further comprises:
a model library is constructed, the model library including a plurality of artificial intelligence program models.
4. The intelligent monitoring method of a nuclear power plant according to claim 3, wherein the building of the model library specifically comprises:
constructing a structure of an artificial intelligence program model according to the configuration of the instrument control system of the nuclear power station and the judgment process when the mth step is manually executed, wherein m is less than or equal to N and is a positive integer;
determining input variables of the artificial intelligence program model according to the monitored information during the artificial execution of the mth step;
and carrying out supervised learning on the artificial intelligence program model based on historical data generated in the process of artificially executing the mth step to generate the artificial intelligence program model corresponding to the mth step, wherein the historical data comprises monitored information and/or control instructions.
5. The intelligent monitoring method for nuclear power plant according to claim 4, wherein after the supervised learning of the artificial intelligence program model based on the historical data generated during the mth step is performed manually to generate the artificial intelligence program model corresponding to the mth step, the method further comprises:
and executing the monitoring task by the generated artificial intelligence program model corresponding to the mth step in the nuclear power station simulator, and collecting data generated in the process of executing the monitoring task to perform reinforcement learning so as to determine the optimal parameters of the artificial intelligence program model corresponding to the mth step.
6. An intelligent monitoring server of a nuclear power station is characterized by comprising a receiving module, an execution module, a sending module and a model library,
the receiving module is used for receiving monitoring data sent by the instrument control system of the nuclear power station in real time,
the execution module is connected with the receiving module and used for calling an automatic program or an artificial intelligence program model in a model base according to the preset sequence control logic of the operation regulation according to the preset operation regulation target and the real-time received monitoring data so as to generate a control instruction required by each step in the sequence control logic for executing the operation regulation,
the sending module is connected with the execution module and is used for sending the control instruction to the instrument control system of the nuclear power station in real time to execute corresponding control so as to realize the autonomous execution of the operation regulation,
and the model library is used for storing a plurality of artificial intelligence program models.
7. The intelligent monitoring server of a nuclear power plant according to claim 6, further comprising a first building module, a determination module, and a second building module,
a first construction module for constructing a sequence control logic of the operation regulation according to the whole processing flow and the branch processing flow of the operation regulation of the nuclear power station, wherein the sequence control logic comprises N steps which are required to be executed in sequence when the operation regulation is executed, N is a positive integer,
the determining module is connected with the constructing module and is used for determining a generating main body of the control instruction corresponding to each step according to the characteristics of each step in the sequence control logic, the generating main body comprises an automatic program or an artificial intelligence program model,
and the second construction module is connected with the determination module and used for constructing a model library, and the model library comprises a plurality of artificial intelligence program models.
8. The intelligent monitoring server of nuclear power plant according to claim 7, wherein the second building module includes a building unit and a training unit,
a construction unit for constructing the structure of the artificial intelligence program model according to the configuration of the nuclear power station instrument control system and the judgment process when the mth step is manually executed, wherein m is less than or equal to N and is a positive integer, determining the input variable of the artificial intelligence program model according to the monitored information when the mth step is manually executed,
and the training unit is connected with the construction unit and used for carrying out supervised learning on the artificial intelligent program model based on historical data generated in the process of artificially executing the mth step so as to generate the artificial intelligent program model corresponding to the mth step, wherein the historical data comprises monitored information and/or control instructions.
9. The intelligent monitoring server of nuclear power plant according to claim 8, wherein the second building module further comprises an optimization unit,
and the optimization unit is connected with the training unit and used for executing the monitoring task on the artificial intelligence program model corresponding to the mth step in the nuclear power plant simulator and collecting data generated in the process of executing the monitoring task to perform reinforcement learning so as to determine the optimal parameters of the artificial intelligence program model corresponding to the mth step.
10. An intelligent monitoring system of a nuclear power plant, which is characterized by comprising a nuclear power plant instrument control system and an intelligent monitoring server of the nuclear power plant according to any one of claims 6 to 9,
the nuclear power station instrument control system is used for monitoring the operation data of equipment in the nuclear power station and sending the monitoring data to an intelligent monitoring server of the nuclear power station in real time,
the intelligent monitoring server of the nuclear power station is connected with the instrument control system of the nuclear power station and is used for receiving monitoring data sent by the instrument control system of the nuclear power station in real time and sending a control command to the instrument control system of the nuclear power station,
and the nuclear power plant instrument control system is also used for executing corresponding control on corresponding equipment in the nuclear power plant according to the control command.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110812520.2A CN113555141B (en) | 2021-07-19 | 2021-07-19 | Intelligent monitoring method and system for nuclear power station and intelligent monitoring server |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110812520.2A CN113555141B (en) | 2021-07-19 | 2021-07-19 | Intelligent monitoring method and system for nuclear power station and intelligent monitoring server |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113555141A true CN113555141A (en) | 2021-10-26 |
| CN113555141B CN113555141B (en) | 2024-04-19 |
Family
ID=78103345
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110812520.2A Active CN113555141B (en) | 2021-07-19 | 2021-07-19 | Intelligent monitoring method and system for nuclear power station and intelligent monitoring server |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113555141B (en) |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103165207A (en) * | 2011-12-13 | 2013-06-19 | 中广核工程有限公司 | Sequential control method and system suitable for nuclear power station |
| CN103441571A (en) * | 2013-06-18 | 2013-12-11 | 国家电网公司 | Integrated monitoring system information platform for transformer substation |
| CN103441570A (en) * | 2013-06-18 | 2013-12-11 | 国家电网公司 | One-button type sequential control operation control method based on integrated information platform |
| CN108321930A (en) * | 2018-01-30 | 2018-07-24 | 珠海华伟电气科技股份有限公司 | A kind of sequence control system and method |
| CN110114806A (en) * | 2018-02-28 | 2019-08-09 | 华为技术有限公司 | Signalized control method, relevant device and system |
| CN110189360A (en) * | 2019-05-28 | 2019-08-30 | 四川大学华西第二医院 | A kind of recognition and tracking method of pair of specific objective |
| CN110639208A (en) * | 2019-09-20 | 2020-01-03 | 超参数科技(深圳)有限公司 | Interactive task control method and device, storage medium and computer equipment |
| CN111614913A (en) * | 2020-05-06 | 2020-09-01 | 许昌许继软件技术有限公司 | One-key sequence control double-confirmation system and method based on intelligent isolation switch position identification |
| CN112016704A (en) * | 2020-10-30 | 2020-12-01 | 超参数科技(深圳)有限公司 | AI model training method, model using method, computer device and storage medium |
| CN112230548A (en) * | 2020-10-27 | 2021-01-15 | 中国核动力研究设计院 | Nuclear power device autonomous control system |
| CN112311098A (en) * | 2020-11-27 | 2021-02-02 | 国网浙江省电力有限公司检修分公司 | Sequence control function debugging system for substation equipment |
-
2021
- 2021-07-19 CN CN202110812520.2A patent/CN113555141B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103165207A (en) * | 2011-12-13 | 2013-06-19 | 中广核工程有限公司 | Sequential control method and system suitable for nuclear power station |
| CN103441571A (en) * | 2013-06-18 | 2013-12-11 | 国家电网公司 | Integrated monitoring system information platform for transformer substation |
| CN103441570A (en) * | 2013-06-18 | 2013-12-11 | 国家电网公司 | One-button type sequential control operation control method based on integrated information platform |
| CN108321930A (en) * | 2018-01-30 | 2018-07-24 | 珠海华伟电气科技股份有限公司 | A kind of sequence control system and method |
| CN110114806A (en) * | 2018-02-28 | 2019-08-09 | 华为技术有限公司 | Signalized control method, relevant device and system |
| CN110189360A (en) * | 2019-05-28 | 2019-08-30 | 四川大学华西第二医院 | A kind of recognition and tracking method of pair of specific objective |
| CN110639208A (en) * | 2019-09-20 | 2020-01-03 | 超参数科技(深圳)有限公司 | Interactive task control method and device, storage medium and computer equipment |
| CN111614913A (en) * | 2020-05-06 | 2020-09-01 | 许昌许继软件技术有限公司 | One-key sequence control double-confirmation system and method based on intelligent isolation switch position identification |
| CN112230548A (en) * | 2020-10-27 | 2021-01-15 | 中国核动力研究设计院 | Nuclear power device autonomous control system |
| CN112016704A (en) * | 2020-10-30 | 2020-12-01 | 超参数科技(深圳)有限公司 | AI model training method, model using method, computer device and storage medium |
| CN112311098A (en) * | 2020-11-27 | 2021-02-02 | 国网浙江省电力有限公司检修分公司 | Sequence control function debugging system for substation equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113555141B (en) | 2024-04-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104635669B (en) | A kind of I＆C system verification method | |
| CN108490906B (en) | Design method for improving DCS (distributed control System) control thermal power generating unit to have complete automatic start-stop function | |
| CN115292885A (en) | Water hammer protection and intelligent regulation and control system for water supply engineering based on digital twin | |
| CN117495356B (en) | Intelligent gas pipeline maintenance method based on man-machine linkage and Internet of things system | |
| Berkan et al. | Advanced automation concepts for large-scale systems | |
| CN115076452A (en) | Health management system and method for one-way valve of high-pressure diaphragm pump based on digital twinning | |
| CN113555141B (en) | Intelligent monitoring method and system for nuclear power station and intelligent monitoring server | |
| CN112230548B (en) | Nuclear power device autonomous control system | |
| CN107863168B (en) | Method for analyzing withdrawal time of nuclear power unit when power operation loses final heat trap | |
| CN113485213A (en) | Intelligent real-time monitoring system for digital twin regulating valve | |
| JPS6252601A (en) | Plant operation supporting system | |
| Husseiny et al. | Operating procedure automation to enhance safety of nuclear power plants | |
| Jharko et al. | Digital twins: Forecasting and formation of optimal control programs for NPP power units | |
| Hanna et al. | Benchmarking an AI-guided reasoning-based operator support system on the three mile island accident scenario | |
| Siqiao et al. | Research on artificial intelligent nuclear power plant emergency operating guide | |
| CN114050651A (en) | New energy power transmission state monitoring method based on artificial intelligence algorithm | |
| Larsson et al. | A revival of the alarm system: Making the alarm list useful during incidents | |
| CN108829057A (en) | System and method is monitored based on different characteristic parameter and logical relation boiler heating surface | |
| CN115705018B (en) | Unmanned station remote monitoring system and unmanned station remote monitoring method | |
| KR102698496B1 (en) | Reinforcement learning model learning method and rule-based nuclear power plant operation automation method using the same | |
| Xu et al. | Fault Diagnosis Analysis of Complex Controlled Process Based on Multilayer Flow Model | |
| Farber et al. | Real-Time Supervisory Control Implementation of SmAHTR Power Plant | |
| Yu et al. | STUDY ON OVERALL CONCEPTUAL SCHEME OF INTELLIGENT OPERATION AND MAINTENANCE SYSTEM FOR MOBILE SMALL MODULAR REACTOR BASED ON SYSTEM ENGINEERING METHOD | |
| CN117250919A (en) | Nuclear power plant control system and control method thereof | |
| CN115840428A (en) | Intelligent water island processing method and system for thermal power plant |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |